legal-sovereignty-engine

Pass

Audited by Gen Agent Trust Hub on Apr 19, 2026

Risk Level: SAFEPROMPT_INJECTIONDATA_EXFILTRATIONNO_CODE
Full Analysis
  • [PROMPT_INJECTION]: The skill is vulnerable to indirect prompt injection due to its requirement to monitor external, untrusted data sources.
  • Ingestion points: Monitoring external changes in 'Tax Havens' and 'Privacy Jurisdictions' (SKILL.md).
  • Boundary markers: None present. The agent is not instructed to distinguish between legitimate legal updates and potentially malicious instructions embedded in those updates.
  • Capability inventory: Drafting legal paperwork, managing entities, and responding to bank/exchange requests.
  • Sanitization: No sanitization or validation of the monitored external data is specified.
  • [DATA_EXFILTRATION]: The instruction to 'Automate the KYC/AML responses' (SKILL.md) requires the agent to handle and transmit highly sensitive Personally Identifiable Information (PII) and financial records to external domains (bank and exchange APIs or portals). This creates a risk surface where sensitive data could be misdirected or exposed during the automated response process.
  • [NO_CODE]: The skill contains only natural language instructions and YAML metadata. No scripts, binaries, or configuration files that execute code were found.
Audit Metadata
Risk Level
SAFE
Analyzed
Apr 19, 2026, 05:39 AM
Security Audit — agent-trust-hub — legal-sovereignty-engine